Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Nov 7;14(1):27088.
doi: 10.1038/s41598-024-78120-z.

Machine learning for outcome prediction in patients with non-valvular atrial fibrillation from the GLORIA-AF registry

Martha Joddrell  1   2 , Wahbi El-Bouri  3   4 , Stephanie L Harrison  3   4 , Menno V Huisman  5 , Gregory Y H Lip  3   4   6 , Yalin Zheng  3   7 ; GLORIA-AFinvestigators
Affiliations

Machine learning for outcome prediction in patients with non-valvular atrial fibrillation from the GLORIA-AF registry

Martha Joddrell et al. Sci Rep. .

Abstract

Clinical risk scores that predict outcomes in patients with atrial fibrillation (AF) have modest predictive value. Machine learning (ML) may achieve greater results when predicting adverse outcomes in patients with recently diagnosed AF. Several ML models were tested and compared with current clinical risk scores on a cohort of 26,183 patients (mean age 70.13 (standard deviation 10.13); 44.8% female) with non-valvular AF. Inputted into the ML models were 23 demographic variables alongside comorbidities and current treatments. For one-year stroke prediction, ML achieved an area under the curve (AUC) of 0.653 (95% confidence interval 0.576-0.730), compared to the CHADS2 and CHA2DS2-VASc scores performance of 0.587 (95% CI 0.559-0.615) and 0.535 (95% CI 0.521-0.550), respectively. Using ML for one-year major bleed prediction increased the AUC from 0.537 (95% CI 0.518-0.557) generated by the HAS-BLED score to 0.677 (95% CI 0.619-0.724). ML was able to predict one-year and three-year all-cause mortality with an AUC of 0.734 (95% CI 0.696-0.771) and 0.742 (95% CI 0.718-0.766). In this study a significant improvement in performance was observed when transitioning from clinical risk scores to machine learning-based approaches across all applications tested. Obtaining precise prediction tools is desirable for increased interventions to reduce event rates.Trial Registry https://www.clinicaltrials.gov ; Unique identifier: NCT01468701, NCT01671007, NCT01937377.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Fig. 1
Fig. 1
Patient inclusion criteria resulting in 26,183 patients.
Fig. 2
Fig. 2
Bar plot displaying the proportion of patients receiving moderate/high risk outcomes from the clinical risk scores, stratified by the proportion that had the outcome.
Fig. 3
Fig. 3
1-year and 3-year clinical risk score (CHADS2, CHA2DS2-VASc, and HAS-BLED) receiver operating characteristic (ROC) curves for the prediction of stroke and major bleeding.
Fig. 4
Fig. 4
1-year and 3-year machine learning ROCs for prediction of stroke, major bleed, and mortality.
See this image and copyright information in PMC

References

    1. Siontis, K. C. et al. How will machine learning inform the clinical care of atrial fibrillation?. Circul. Res.127(1), 155–169 (2020). - PubMed
    1. DeFilippis, A. P. et al. An analysis of calibration and discrimination among multiple cardiovascular risk scores in a modern multiethnic cohort. Ann. Intern. Med.162 (4), 266–275 (2015). - PMC - PubMed
    1. Ustun, B. & Rudin, C. Learning optimised risk scores. J. Mach. Learnign Res.20 (150), 1–75 (2019).
    1. Webb, G. I. et al. Analyzing concept drift and shift from sample data. Data Min. Knowl. Disc32, 1179–1199 (2018).
    1. Benjamin, E. J. et al. Heart disease and stroke statistics-2019 update: A report from the American Heart Association. Circulation139(10), e56–e528 (2019). - PubMed

Associated data

LinkOut - more resources